Evaluation of eye-tracking methods for a decision support application

Eye-tracking is used widely to investigate visual and cognitive processes in the context of electronic medical record systems. We investigated a novel application of eye tracking to collect training data for machine learning-based clinical decision support. Specifically, we recorded the information-seeking behavior of physicians while they used electronic medical records in the context of a specific clinical task. Using data captured by a low-cost eye tracking device, we evaluated the performance of several methods for processing gaze points that were recorded using the device. Our results support the use of a low-cost eye tracking device and relatively simple methods for processing gaze points to record the information-seeking behavior of physicians. The eye-tracking methods and scripts that we developed offer a first step in developing novel uses for eye-tracking for clinical decision support.

[1]  Christian Lovis,et al.  Use of eye-tracking technology in clinical reasoning: a systematic review , 2015, MIE.

[2]  Dean F. Sittig,et al.  Modeling physician variability to prioritize relevant medical record information , 2020, medRxiv.

[3]  Gilles Clermont,et al.  Eye-tracking for clinical decision support: A method to capture automatically what physicians are viewing in the EMR , 2017, CRI.

[4]  Nadir Weibel,et al.  Eyes on the clinic: Accelerating meaningful interface analysis through unobtrusive eye tracking , 2015, 2015 9th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth).

[5]  Ze He,et al.  Using High-Fidelity Simulation and Eye Tracking to Characterize Workflow Patterns among Hospital Physicians , 2015, AMIA.

[6]  Agostino Gibaldi,et al.  Evaluation of the Tobii EyeX Eye tracking controller and Matlab toolkit for research , 2016, Behavior Research Methods.

[7]  Using machine learning to selectively highlight patient information , 2019, J. Biomed. Informatics.

[8]  Andrew J King,et al.  Leveraging Eye Tracking to Prioritize Relevant Medical Record Data: Comparative Machine Learning Study , 2020, Journal of medical Internet research.

[9]  Gilles Clermont,et al.  Using Machine Learning to Predict the Information Seeking Behavior of Clinicians Using an Electronic Medical Record System , 2018, AMIA.

[10]  Yushi Yang,et al.  Using Eye Trackers for Usability Evaluation of Health Information Technology: A Systematic Literature Review , 2015, JMIR human factors.